Triple

T12683497
Position Surface form Disambiguated ID Type / Status
Subject Netherland Dwarf E303005 entity
Predicate hasCastMember P2308 FINISHED
Object Ewen Leslie E902655 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Ewen Leslie | Statement: [Netherland Dwarf, hasCastMember, Ewen Leslie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ewen Leslie
Context triple: [Netherland Dwarf, hasCastMember, Ewen Leslie]
  • A. Ewen Leslie chosen
    Ewen Leslie is an Australian actor known for his acclaimed work in film, television, and theatre.
  • B. Greg McEwan
    Greg McEwan is a child of the acclaimed British novelist Ian McEwan.
  • C. Ewen Macdonald
    Ewen Macdonald was a Presbyterian minister best known as the husband of Canadian author Lucy Maud Montgomery.
  • D. Leo Docherty
    Leo Docherty is a British Conservative Party politician and Member of Parliament known for representing the Aldershot constituency.
  • E. Clive Egleton
    Clive Egleton was a British author best known for his espionage and military thrillers, several of which were adapted for film and television.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d7bdee64a08190801c6d470aefd723 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961d68358819095bdaab8adf1dcf0 completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5b9e0c4819095194dc42677e17f completed May 3, 2026, 7:14 a.m.
Created at: April 9, 2026, 5:21 p.m.